BR102019001258A2 - método, aparelho e programa de computador para geração de sistemas de aprendizado automatizados robustos e teste de sistemas de aprendizado automatizados treinados - Google Patents
método, aparelho e programa de computador para geração de sistemas de aprendizado automatizados robustos e teste de sistemas de aprendizado automatizados treinados Download PDFInfo
- Publication number
- BR102019001258A2 BR102019001258A2 BR102019001258A BR102019001258A BR102019001258A2 BR 102019001258 A2 BR102019001258 A2 BR 102019001258A2 BR 102019001258 A BR102019001258 A BR 102019001258A BR 102019001258 A BR102019001258 A BR 102019001258A BR 102019001258 A2 BR102019001258 A2 BR 102019001258A2
- Authority
- BR
- Brazil
- Prior art keywords
- learning system
- automated learning
- value
- input
- layer
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 121
- 238000012360 testing method Methods 0.000 title claims abstract description 46
- 238000013528 artificial neural network Methods 0.000 claims abstract description 116
- 238000012549 training Methods 0.000 claims abstract description 80
- 230000000644 propagated effect Effects 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 145
- 238000012986 modification Methods 0.000 claims description 78
- 230000004048 modification Effects 0.000 claims description 78
- 239000011159 matrix material Substances 0.000 claims description 52
- 230000001419 dependent effect Effects 0.000 claims description 36
- 230000009466 transformation Effects 0.000 claims description 34
- 230000008859 change Effects 0.000 claims description 26
- 238000005457 optimization Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 10
- 230000001902 propagating effect Effects 0.000 claims description 9
- 238000012886 linear function Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000000844 transformation Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 240000006927 Foeniculum vulgare Species 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims 3
- 230000017105 transposition Effects 0.000 claims 1
- 230000004913 activation Effects 0.000 description 42
- 238000001994 activation Methods 0.000 description 42
- 210000002569 neuron Anatomy 0.000 description 17
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000002411 adverse Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000005406 washing Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 241000196324 Embryophyta Species 0.000 description 3
- 238000013475 authorization Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000009187 flying Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 241000209202 Bromus secalinus Species 0.000 description 1
- AZFKQCNGMSSWDS-UHFFFAOYSA-N MCPA-thioethyl Chemical compound CCSC(=O)COC1=CC=C(Cl)C=C1C AZFKQCNGMSSWDS-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000009189 diving Effects 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010413 gardening Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009183 running Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000009184 walking Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Feedback Control In General (AREA)
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US201862677896P | 2018-05-30 | 2018-05-30 | |
| US201862736858P | 2018-09-26 | 2018-09-26 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| BR102019001258A2 true BR102019001258A2 (pt) | 2019-12-03 |
Family
ID=66589347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| BR102019001258A BR102019001258A2 (pt) | 2018-05-30 | 2019-01-22 | método, aparelho e programa de computador para geração de sistemas de aprendizado automatizados robustos e teste de sistemas de aprendizado automatizados treinados |
Country Status (9)
| Country | Link |
|---|---|
| US (2) | US11676025B2 (zh) |
| EP (1) | EP3576021A1 (zh) |
| KR (1) | KR20190136893A (zh) |
| CN (1) | CN110554602A (zh) |
| AU (1) | AU2018256516A1 (zh) |
| BR (1) | BR102019001258A2 (zh) |
| CA (1) | CA3022728A1 (zh) |
| DE (1) | DE102018218586A1 (zh) |
| MX (1) | MX2018013242A (zh) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11547052B1 (en) * | 2018-10-10 | 2023-01-10 | Hydro-Gear Limited Partnership | Audible operator feedback for riding lawn mower applications |
| US11200438B2 (en) | 2018-12-07 | 2021-12-14 | Dus Operating Inc. | Sequential training method for heterogeneous convolutional neural network |
| US11200318B2 (en) * | 2018-12-28 | 2021-12-14 | Mcafee, Llc | Methods and apparatus to detect adversarial malware |
| US11625487B2 (en) * | 2019-01-24 | 2023-04-11 | International Business Machines Corporation | Framework for certifying a lower bound on a robustness level of convolutional neural networks |
| US11068069B2 (en) * | 2019-02-04 | 2021-07-20 | Dus Operating Inc. | Vehicle control with facial and gesture recognition using a convolutional neural network |
| CN111027628B (zh) * | 2019-12-12 | 2022-03-11 | 支付宝(杭州)信息技术有限公司 | 一种模型确定方法和系统 |
| US10846407B1 (en) | 2020-02-11 | 2020-11-24 | Calypso Ai Corp | Machine learning model robustness characterization |
| US11568021B2 (en) | 2020-02-21 | 2023-01-31 | Alibaba Group Holding Limited | Vector-vector multiplication techniques for processing systems |
| CN111368886B (zh) * | 2020-02-25 | 2023-03-21 | 华南理工大学 | 一种基于样本筛选的无标注车辆图片分类方法 |
| DE102020202870A1 (de) * | 2020-03-06 | 2021-09-09 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zur Validierung und Auswahl auf maschinellem Lernen basierender Modelle zur Zustandsüberwachung einer Maschine |
| CN111401292B (zh) * | 2020-03-25 | 2023-05-26 | 成都东方天呈智能科技有限公司 | 一种融合红外图像训练的人脸识别网络构建方法 |
| CN111461307B (zh) * | 2020-04-02 | 2022-04-29 | 武汉大学 | 一种基于生成对抗网络的通用扰动生成方法 |
| EP3896613B1 (en) * | 2020-04-14 | 2024-06-05 | Robert Bosch GmbH | Device and method for training a classifier and assessing the robustness of a classifier |
| US20210334646A1 (en) * | 2020-04-28 | 2021-10-28 | International Business Machines Corporation | Robustness-aware quantization for neural networks against weight perturbations |
| DE102020114339A1 (de) * | 2020-05-28 | 2021-12-02 | Ebm-Papst Mulfingen Gmbh & Co. Kg | Verfahren zum Betreiben eines Ventilatorsystems und Ventilatorsystem mit einem rückwärtsgekrümmten Radialventilator |
| CN111709878B (zh) | 2020-06-17 | 2023-06-23 | 北京百度网讯科技有限公司 | 人脸超分辨率实现方法、装置、电子设备及存储介质 |
| DE102020208737A1 (de) | 2020-07-13 | 2022-01-13 | Volkswagen Aktiengesellschaft | Verfahren und Vorrichtung zum Bewerten und Zertifizieren einer Robustheit eines KI-basierten Informationsverarbeitungssystems |
| KR102598909B1 (ko) * | 2020-09-03 | 2023-11-06 | 부산대학교 산학협력단 | 적대적 사례에 강인한 심층 신경망 모델을 위한 입력 장치 및 방법 |
| US11687619B2 (en) * | 2020-10-02 | 2023-06-27 | Robert Bosch Gmbh | Method and system for an adversarial training using meta-learned initialization |
| DE102020213058A1 (de) | 2020-10-15 | 2022-04-21 | Volkswagen Aktiengesellschaft | Verfahren und Vorrichtung zum teilautomatisierten oder vollautomatisierten Steuern eines Fahrzeugs |
| DE102020213057A1 (de) | 2020-10-15 | 2022-04-21 | Volkswagen Aktiengesellschaft | Verfahren und Vorrichtung zum Überprüfen eines beim teilautomatisierten oder vollautomatisierten Steuern eines Fahrzeugs verwendeten KI-basierten Informationsverarbeitungssystems |
| JP2022085164A (ja) | 2020-11-27 | 2022-06-08 | ロベルト・ボッシュ・ゲゼルシャフト・ミト・ベシュレンクテル・ハフツング | データ処理装置、ニューラルネットワークの深層学習の方法及びプログラム |
| US11907334B2 (en) * | 2020-12-08 | 2024-02-20 | International Business Machines Corporation | Neural network negative rule extraction |
| CN114200841B (zh) * | 2021-12-13 | 2023-05-23 | 电子科技大学 | 一种基于模糊反步的网联汽车系统安全控制方法 |
| CN115114395B (zh) * | 2022-04-15 | 2024-03-19 | 腾讯科技（深圳）有限公司 | 内容检索及模型训练方法、装置、电子设备和存储介质 |
| CN114756214B (zh) * | 2022-06-15 | 2022-08-12 | 中国海洋大学 | 基于OpenCV和插件的图像处理方法、装置 |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4884216A (en) * | 1987-11-09 | 1989-11-28 | Michael Kuperstein | Neural network system for adaptive sensory-motor coordination of multijoint robots for single postures |
| US8688616B2 (en) * | 2010-06-14 | 2014-04-01 | Blue Prism Technologies Pte. Ltd. | High-dimensional data analysis |
| US8712940B2 (en) * | 2011-05-31 | 2014-04-29 | International Business Machines Corporation | Structural plasticity in spiking neural networks with symmetric dual of an electronic neuron |
| CN104392143B (zh) * | 2014-12-09 | 2017-05-17 | 北京四方继保自动化股份有限公司 | 一种自适应量子神经网络汽轮机故障趋势预测方法 |
| CN105512725B (zh) * | 2015-12-14 | 2018-08-28 | 杭州朗和科技有限公司 | 一种神经网络的训练方法和设备 |
| US11144889B2 (en) * | 2016-04-06 | 2021-10-12 | American International Group, Inc. | Automatic assessment of damage and repair costs in vehicles |
| US10810481B2 (en) * | 2017-01-11 | 2020-10-20 | Thomas Danaher Harvey | Method and system to count movements of persons from vibrations in a floor |
| DE102018200724A1 (de) | 2017-04-19 | 2018-10-25 | Robert Bosch Gmbh | Verfahren und Vorrichtung zum Verbessern der Robustheit gegen "Adversarial Examples" |
| WO2019227294A1 (zh) * | 2018-05-28 | 2019-12-05 | 华为技术有限公司 | 图像处理方法、相关设备及计算机存储介质 |
| DE102018208763A1 (de) | 2018-06-04 | 2019-12-05 | Robert Bosch Gmbh | Verfahren, Vorrichtung und Computerprogramm zum Betreiben eines maschinellen Lernsystems |
-
2018
- 2018-10-29 KR KR1020180130138A patent/KR20190136893A/ko unknown
- 2018-10-29 CN CN201811268424.0A patent/CN110554602A/zh active Pending
- 2018-10-29 US US16/173,126 patent/US11676025B2/en active Active
- 2018-10-29 US US16/173,698 patent/US11386328B2/en active Active
- 2018-10-29 MX MX2018013242A patent/MX2018013242A/es unknown
- 2018-10-30 AU AU2018256516A patent/AU2018256516A1/en not_active Abandoned
- 2018-10-30 CA CA3022728A patent/CA3022728A1/en active Pending
- 2018-10-30 DE DE102018218586.7A patent/DE102018218586A1/de active Pending
-
2019
- 2019-01-22 BR BR102019001258A patent/BR102019001258A2/pt not_active IP Right Cessation
- 2019-05-16 EP EP19174931.6A patent/EP3576021A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| MX2018013242A (es) | 2019-12-02 |
| DE102018218586A1 (de) | 2020-01-09 |
| KR20190136893A (ko) | 2019-12-10 |
| US20190370660A1 (en) | 2019-12-05 |
| AU2018256516A1 (en) | 2019-12-19 |
| CN110554602A (zh) | 2019-12-10 |
| US11386328B2 (en) | 2022-07-12 |
| CA3022728A1 (en) | 2019-11-30 |
| US20200026996A1 (en) | 2020-01-23 |
| EP3576021A1 (en) | 2019-12-04 |
| US11676025B2 (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| BR102019001258A2 (pt) | método, aparelho e programa de computador para geração de sistemas de aprendizado automatizados robustos e teste de sistemas de aprendizado automatizados treinados | |
| US11586911B2 (en) | Pre-training system for self-learning agent in virtualized environment | |
| US11514297B2 (en) | Post-training detection and identification of human-imperceptible backdoor-poisoning attacks | |
| KR102450374B1 (ko) | 데이터 인식 및 트레이닝 장치 및 방법 | |
| Zhang et al. | Fruit classification by biogeography‐based optimization and feedforward neural network | |
| Bendale et al. | Towards open set deep networks | |
| US10769261B2 (en) | User image verification | |
| US11475130B2 (en) | Detection of test-time evasion attacks | |
| US20160335540A1 (en) | System and method for addressing overfitting in a neural network | |
| KR102374747B1 (ko) | 객체를 인식하는 장치 및 방법 | |
| KR20160061856A (ko) | 객체 인식 방법 및 장치, 및 인식기 학습 방법 및 장치 | |
| Chacon et al. | Deep learning poison data attack detection | |
| Huang et al. | Uncertainty-aware learning against label noise on imbalanced datasets | |
| US20210216857A1 (en) | Device and method for training an augmented discriminator | |
| EP3754557A1 (en) | Robustness indicator unit, certificate determination unit, training unit, control unit and computer-implemented method to determine a robustness indicator | |
| US20230049479A1 (en) | Computer-implemented method for accelerating convergence in the training of generative adversarial networks (gan) to generate synthetic network traffic, and computer programs of same | |
| Lorenz et al. | Is robustbench/autoattack a suitable benchmark for adversarial robustness? | |
| Soares | Formalizing two problems of realistic world-models | |
| KR20200052068A (ko) | 눈 추적 방법 및 장치 | |
| US11507670B2 (en) | Method for testing an artificial intelligence model using a substitute model | |
| Lu et al. | Ranking attack graphs with graph neural networks | |
| Zennayi et al. | Unauthorized access detection system to the equipments in a room based on the persons identification by face recognition | |
| KR20230057765A (ko) | 자기-지도 학습 기반의 다중 객체 추적 장치 및 방법 | |
| Alrawashdeh et al. | Defending deep learning based anomaly detection systems against white-box adversarial examples and backdoor attacks | |
| Liu et al. | Model Stealing Detection for IoT Services Based on Multi-Dimensional Features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| B03A | Publication of a patent application or of a certificate of addition of invention [chapter 3.1 patent gazette] | ||
| B08F | Application dismissed because of non-payment of annual fees [chapter 8.6 patent gazette] |
Free format text: REFERENTE A 5A ANUIDADE. |
|
| B08K | Patent lapsed as no evidence of payment of the annual fee has been furnished to inpi [chapter 8.11 patent gazette] |
Free format text: EM VIRTUDE DO ARQUIVAMENTO PUBLICADO NA RPI 2758 DE 14-11-2023 E CONSIDERANDO AUSENCIA DE MANIFESTACAO DENTRO DOS PRAZOS LEGAIS, INFORMO QUE CABE SER MANTIDO O ARQUIVAMENTO DO PEDIDO DE PATENTE, CONFORME O DISPOSTO NO ARTIGO 12, DA RESOLUCAO 113/2013. |